# Reconstruction: A Blind Benchmark for Recovering Research Ideas from Pre-Publication Bibliographies

arXiv: https://arxiv.org/abs/2608.16645 · HTML: https://mlsanity.com/paper/2608.16645/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 31 references that are in the map.
- First posted on arXiv 17 Aug 2026.

## Builds on (most cited first, 21 of 21)

- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers](https://mlsanity.com/paper/2409.04109/) (2024)
- [ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models](https://mlsanity.com/paper/2404.07738/) (2024)
- [Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agents](https://mlsanity.com/paper/2410.13185/) (2024)
- [MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses](https://mlsanity.com/paper/2410.07076/) (2024)
- [ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition](https://mlsanity.com/paper/2503.21248/) (2025)
- [The Ideation-Execution Gap: Execution Outcomes of LLM-Generated versus Human Research Ideas](https://mlsanity.com/paper/2506.20803/) (2025)
- [How much do language models memorize?](https://mlsanity.com/paper/2505.24832/) (2025)
- [AI Idea Bench 2025: AI Research Idea Generation Benchmark](https://mlsanity.com/paper/2504.14191/) (2025)
- [HindSight: Evaluating LLM-Generated Research Ideas via Future Impact](https://mlsanity.com/paper/2603.15164/) (2026)
- [Is this Idea Novel? An Automated Benchmark for Judgment of Research Ideas](https://mlsanity.com/paper/2603.10303/) (2026)
- [Measuring the Gap Between Human and LLM Research Ideas](https://mlsanity.com/paper/2607.01233/) (2026)
- [Deep Ideation: Designing LLM Agents to Generate Novel Research Ideas on Scientific Concept Network](https://mlsanity.com/paper/2511.02238/) (2025)
- [On the ranking of a Swiss system chess team tournament](https://mlsanity.com/paper/1507.05045/) (2015)
- [ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes](https://mlsanity.com/paper/2607.04439/) (2026)

## Built on by (most cited first, 1 of 1)

- [Priced Guidance: Can Language Models Generate Future Research Ideas?](https://mlsanity.com/paper/2610.04976/) (2026)

## Abstract (arXiv)

Can a language model recover the true research idea of a published paper when given only that paper's pre-publication bibliography? We introduce Reconstruction, a blind idea-recovery benchmark that withholds the seed paper and all contemporaneous or future literature, and asks models to propose hypotheses that an independent large language model judge matches against the held-out ground-truth idea. A strict anti-leakage protocol-temporal citation cutoff, anonymous reference IDs, and frozen per-paper bibliographies, which prevents prompt-time leakage of the seed idea. Across six scientific domains and 643 evaluated papers, seven frontier models achieve only modest Match rates (approx. 3-15%). We then evaluate a reference-only multi-agent (top 4) pipeline that combines cross-model review with a Swiss tournament over aligned hypothesis slots, without external web search. Cross-model review plus tournament selection raises Match rates to approx. 23-42% across all six domains, which is an observed approx. 2.4x lift over the best single-model baseline. This draft reports the protocol, anti-leakage design, and current results as an arXiv timestamp.